mini-swe-agent
Shares rank 32 of 41 coding agents by recommenders
Minimal coding agent running an LLM in a loop with only terminal access; praised for simplicity. Critics note it now exceeds its original 100 lines.
Minimal coding agent running an LLM in a loop with only terminal access; praised for simplicity. Critics note it now exceeds its original 100 lines.
10 people gave an opinion
- recommend it
- 9
- criticize it
- 1
- approval share
- 90%
Recommended in 6 of 13 months
- November 2025: not recommended
- December 2025: recommended
- January 2026: recommended
- February 2026: not recommended
- March 2026: not recommended
- April 2026: not recommended
- May 2026: recommended
- June 2026: not recommended
- July 2026: not recommended
- August 2026: recommended
- September 2026: recommended
- October 2026: recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 9 people recommend itNeeds 10 or more, not met.
- 9 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 6 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Minimal, started at 100 lines
“a 100 LoC "LLM in a loop with just terminal access", it is now above last year's heavily harnessed SotA.”
Comment from 22 Dec 2025 in “Claude Code gets native LSP support” “A 100 loc "harness" that is basically a llm in a loop with just a "bash" tool is way better today”
Comment from 14 Jan 2026 in “Claude Cowork Exfiltrates Files” “probably the most minimal agent out there (it started as just 100 lines, all included)”
Comment from 18 Sep 2026 in “An empirical study of harness design for coding agents” - Comment from 18 Sep 2026 in “An empirical study of harness design for coding agents”
Strong results against heavier harnesses
“a 100 LoC "LLM in a loop with just terminal access", it is now above last year's heavily harnessed SotA.”
Comment from 22 Dec 2025 in “Claude Code gets native LSP support” “started to get close to the engineered agents this year”
Comment from 2 Dec 2025 in “AI agents find $4.6M in blockchain smart contract exploits” Adopted by academic and industry labs
“now pretty popular in both academic and industry labs”
Comment from 8 Jan 2026 in “How to Code Claude Code in 200 Lines of Code” “normalizing the harness to mini-swe-agent”
Comment from 27 May 2026 in “DeepSWE: A contamination-free benchmark for long-horizon coding agents”
Other coding agents people recommend
The four most recommended other coding agents, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| GitHub Copilot | 571 | 993 | 37% | 12 | 1 yr46 owners | — |
| oh-my-pi | 104 | 28 | 79% | 9 | 2 mo5 owners | Approved |
| Grok Build CLI | 66 | 114 | 37% | 6 | — | — |
| DeepSeek Harness | 63 | 28 | 69% | 4 | 1 mo5 owners | Approved |
| mini-swe-agentThis page | 9 | 1 | 90% | 6 | — | — |
What people said
11 of the 12 comments that mention it, newest first. Each links to the original comment.
“agent owns the conversation history, this is the right design for an autonomous agent”
“It is way more than 100 lines. Why keep advertising something that is no longer the case?”
“it started as just 100 lines, all included”
“probably the most minimal agent out there (it started as just 100 lines, all included)”
“found it way faster than codex (for small tasks)”
“normalizing the harness to mini-swe-agent”
“install Mini-SWE-Agent and play with that to get a feel for what's going on”
“A 100 loc "harness" that is basically a llm in a loop with just a "bash" tool is way better today”
“now pretty popular in both academic and industry labs”
“a 100 LoC "LLM in a loop with just terminal access", it is now above last year's heavily harnessed SotA.”
“started to get close to the engineered agents this year”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.